Abraham Wald was a Hungarian mathematician who lived in the first half of the last century. His main field was statistical analysis but, being a Jew, he never really had the chance to fully apply his skills in Austria, where he graduated, due to Nazis invasion. In 1938 Wald escaped to the states where he was invited to work at the Columbia University. Thanks to his skills he became a member of the Statistical Research Group (SRG). The SRG was a group of scientists and mathematicians dedicated to solving various wartime problems.
Wald was involved in a famous story that is widely used to explain the Survivor Bias. I read this story many times, but only yesterday I learned his name.
These are the words of W. Allen Wallis, another member of the SRG; “The military was inclined to provide protection for those parts that on returning planes showed the most hits. Wald assumed, on good evidence, that hits in combat were uniformly distributed over the planes. It follows that hits on the more vulnerable parts were less likely to be found on returning planes than hits on the less vulnerable parts, since planes receiving hits on the more vulnerable parts were less likely to return to provide data. From these premises, he devised methods for estimating vulnerability of various parts.”
This story explains perfectly the Survivor Bias. Because we have plenty of information on the survivors from a challenge while we have no info about all the others that didn’t survive (the planes that didn’t come back), we tend to model our behaviours only on the winner (survivors) missing valuable information.
I wrote about Wald this morning because, in the period where superheroes bring billions of people to the cinema, I love the story of a hero whose superpowers are very human: numbers, logic and intuition.
The second reason is that the tale as it is usually told doesn’t give full justice to the scientific work behind it.
You can find more at this link.